A distributed learning proposal to improve industrial processes
Contenido principal del artículo
Resumen
A distributed learning algorithm has been developed, focused on leveraging valuable information from industrial processes of various clients. This algorithm significantly improves the predictive capabilities of Machine Learning models by allowing access to a larger pool of training data. This is achieved by sharing the weights of the models among different participants, without the need to exchange the data itself, ensuring that each client maintains the privacy and security of their information. Thus, this approach not only optimizes the performance of the models individually but also enhances the overall level of artificial intelligence applied in the industrial sector.
Palabras clave:
Detalles del artículo
Citas
FederatedAI, 2024. FederatedAI (FATE): Federated Learning Framework for Secure and Privacy-Preserving AI. https://federatedai.org/.
Liu, Y., Kang, Y., Zou, T., Pu, Y., He, Y., Ye, X., Ouyang, Y., Zhang, Y.-Q., Yang, Q., 2024. Vertical federated learning: Concepts, advances, and challenges. IEEE Transactions on Knowledge and Data Engineering, 1–20.
DOI: 10.1109/tkde.2024.3352628 DOI: https://doi.org/10.1109/TKDE.2024.3352628
Mayer, R., Jacobsen, H.-A., 2020. Distributed and parallel machine learning: A comprehensive review. Journal of Parallel and Distributed Computing. Su, W., Li, L., Liu, F., He, M., Liang, X., 2022. Ai on the edge: a comprehensive review. Artificial Intelligence Review 55 (8), 6125–6183. DOI: https://doi.org/10.1007/s10462-022-10141-4
Tang, Z., Shi, S., Chu, X., Wang, W., Li, B., 2020. Communicationefficient distributed deep learning: A comprehensive survey. CoRR abs/2003.06307. URL: https://arxiv.org/abs/2003.06307
TensorFlow, 2023a. Cifar-10 dataset in tensorflow datasets. URL: https://www.tensorflow.org/datasets/catalog/cifar10
TensorFlow, 2023b. Emnist dataset in tensorflow datasets. URL: https://www.tensorflow.org/datasets/catalog/emnist
Zhang, W., Wang, X., Zhou, P., Wu, W., Zhang, X., 2021. Client selection for federated learning with non-iid data in mobile edge computing. IEEE Access 9, 24462–24474. DOI: 10.1109/ACCESS.2021.3056919 DOI: https://doi.org/10.1109/ACCESS.2021.3056919